A Super Voxel-Based Riemannian Graph for Multi Scale Segmentation of Lidar Point Clouds

Abstract

ABSTRACT:Automatically segmenting LiDAR points into respective independent partitions has become a topic of great importance in photogrammetry, remote sensing and computer vision. In this paper, we cast the problem of point cloud segmentation as a graph optimization problem by constructing a Riemannian graph. The scale space of the observed scene is explored by an octree-based oversegmentation with different depths. The over-segmentation produces many super voxels which restrict the structure of the scene and will be used as nodes of the graph. The Kruskal coordinates are used to compute edge weights that are proportional to the geodesic distance between nodes. Then we compute the edge-weight matrix in which the elements reflect the sectional curvatures associated with the geodesic paths between super voxel nodes on the scene surface. The final segmentation results are generated by clustering similar super voxels and cutting off the weak edges in the graph. The performance of this method was evaluated on LiDAR point clouds for both indoor and outdoor scenes. Additionally, extensive comparisons to state of the art techniques show that our algorithm outperforms on many metrics.

Building Component Detection on Unstructured 3D Indoor Point Clouds Using RANSAC-Based Region Growing

“…PCD acquired from large objects such as the indoors have numerous points, requiring excessive time for data processing if object detection is conducted on all points [51,52]. Thus, PCD with many planar objects (e.g., walls, floors, and ceilings) such as the case with indoor environments have a low accuracy reduction rate for data through data decomposition, which is why voxels are mainly used in object detection [53][54][55]. However, if voxels were produced according to whether points exist, a voxel with many points and one created by outlier would be regarded as the same point.…”

Classification of LiDAR Point Clouds Using Supervoxel-Based Detrended Feature and Perception-Weighted Graphical Model

“…Besides, the construction of graphical models or Markov networks also plays a vital role for the optimization or regularization, which should consider both the spatial relationship (e.g., topology) and defined weights (e.g., similarity or proximity) between points. The graph can be built not only based on a KNN structure [36], but also the one considering manifold structure, like Riemannian graph [44]. The optimization or regularization is achieved by solving the cost function formulated from the graphical models or Markov networks.…”

“…Our proposed boundary refined supervoxel is based on the original VCCS supervoxel, consisting of two major steps, namely, the detection of boundary points, and the refinement of boundary points. In the first step, all the points of one supervoxel will be measured by the distance from the point to the center of the supervoxel considering the local curvature [44] exploring the spatial proximity of adjacent supervoxels in geodetic space.…”

Supervoxel-Based Multi-Scale Point Cloud Segmentation Using Fnea for Object-Oriented Rock Slope Classification Using TLS

“…This step will markedly simplify the complexity involved in subsequent steps of point cloud segmentation and classification within the object-based model and also reduces the computational cost. Similar to the superpixel methods in computer vision, recent developments in the 3D domain compute supervoxels from a set of voxels (Aijazi et al, 2013;Li, 2018;Papon et al, 2013) (Figure 1). In the current study, supervoxels were generated using a 3D modification of the Fractal Net Evolution Approach (FNEA) which was originally developed for coloured 2D image processing.…”